sheoyon-jhin/ANCDE
Attentive Neural Controlled Differential Equations for Time-series Classification and Forecasting
This project offers a powerful method for analyzing time-series data, helping you categorize events or predict future trends even when data points are unevenly spaced or some are missing. You input raw, often irregular, time-series data like patient vital signs or stock prices, and it outputs classifications (e.g., "sepsis detected") or forecasts (e.g., "next quarter's sales"). It's designed for data scientists or researchers who work with complex, real-world sequences where understanding key moments is crucial.
No commits in the last 6 months.
Use this if you need to accurately classify or forecast based on time-series data that is often irregular, has missing values, or requires identifying specific influential moments within the sequence.
Not ideal if your time-series data is perfectly regular, dense, and you don't require an attention mechanism to understand which parts of the series are most impactful.
Stars
45
Forks
9
Language
Python
License
—
Category
Last pushed
Nov 08, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sheoyon-jhin/ANCDE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sktime/sktime
A unified framework for machine learning with time series
aeon-toolkit/aeon
A toolkit for time series machine learning and deep learning
Nixtla/neuralforecast
Scalable and user friendly neural :brain: forecasting algorithms.
tslearn-team/tslearn
The machine learning toolkit for time series analysis in Python
Nixtla/mlforecast
Scalable machine 🤖 learning for time series forecasting.